Update MODEL_SUMMARY.txt - Run 20251104_122236

weights/David-partial_shared-geometric_attention/20251104_122236/MODEL_SUMMARY.txt

@@ -0,0 +1,57 @@
+
+╔══════════════════════════════════════════════════════════════╗
+║                      DAVID MODEL SUMMARY                      ║
+╠══════════════════════════════════════════════════════════════╣
+║                                                               ║
+║  🎯 VALIDATION ACCURACY: 76.11%                          ║
+║                                                               ║
+╚══════════════════════════════════════════════════════════════╝
+
+MODEL: David-partial_shared-geometric_attention
+RUN ID: 20251104_122236
+BEST EPOCH: 1/5
+
+═══════════════════════════════════════════════════════════════
+
+📊 PERFORMANCE BREAKDOWN
+
+Final Training Accuracy:  71.75%
+Best Validation Accuracy: 76.11%
+
+Per-Scale Accuracies:
+  • Scale  256: 74.25%
+  • Scale  512: 75.16%
+  • Scale  768: 75.26%
+  • Scale 1024: 75.82%
+
+═══════════════════════════════════════════════════════════════
+
+🏗️  ARCHITECTURE
+
+Preset:        clip_vit_b16_geometric
+Sharing Mode:  partial_shared
+Fusion Mode:   geometric_attention
+Scales:        4 scales - [256, 512, 768, 1024]
+Feature Dim:   512
+Parameters:    12,599,556
+
+═══════════════════════════════════════════════════════════════
+
+📈 TRAINING CURVE
+
+Epoch | Train Acc | Val Acc  | Learning Rate
+------|-----------|----------|--------------
+    1 |    71.75% |   76.11% 👑 | 9.76e-04
+
+═══════════════════════════════════════════════════════════════
+
+📁 FILES
+
+Best Model:    best_model_acc76.11.safetensors
+Config:        david_config.json
+Training Cfg:  train_config.json
+History:       training_history.json
+
+═══════════════════════════════════════════════════════════════
+
+Generated: 2025-11-04 12:24:27